Using Semantic Information to Improve Generalization of Reinforcement Learning Policies for Autonomous Driving

Florence Carton, David Filliat, Jaonary Rabarisoa, Quoc Cuong Pham; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2021, pp. 144-151

Abstract

The problem of generalization of reinforcement learning policies to new environments is seldom addressed but essential in practical applications. We focus on this problem in an autonomous driving context using the CARLA simulator and first show that semantic information is the key to a good generalization for this task. We then explore and compare different classical ways to improve generalization in an unseen environment without finetuning, showing that using semantic segmentation as an auxiliary task is the most efficient approach.

Related Material

[pdf]
[bibtex]
@InProceedings{Carton_2021_WACV, author = {Carton, Florence and Filliat, David and Rabarisoa, Jaonary and Pham, Quoc Cuong}, title = {Using Semantic Information to Improve Generalization of Reinforcement Learning Policies for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {January}, year = {2021}, pages = {144-151} }